US8249880B2 - Real-time display of system instructions - Google Patents

Abstract

A system and method for reviewing inputted voice instructions in a vehicle-based telematics control unit. The system includes a microphone, a speech recognition processor, and an output device. The microphone receives voice instructions from a user. Coupled to the microphone is the speech recognition processor that generates a voice signal by performing speech recognition processing of the received voice instructions. The output device outputs the generated voice signal to the user. The system also includes a user interface for allowing the user to approve the outputted voice signal, and a communication component for wirelessly sending the generated voice signal to a server over a wireless network upon approval by the user.

Description

CROSS-REFERENCE TO RELATED APPLICATION

This application is a continuation of and claims priority to Ser. No. 11/929,656, now U.S. Pat. No. 7,801,731 filed Oct. 30, 2007 and 10/076,874, now U.S. Pat. No. 7,406,421 filed Feb. 14, 2002, which are hereby incorporated by reference in their entireties.

FIELD OF THE INVENTION

This invention relates generally to the field of vehicle user interfaces.

BACKGROUND OF THE INVENTION

Various vehicle devices exist that are designed to provide a vehicle operator with travel-related information. For example, a display coupled to a global positioning system (GPS) may be used to present to the vehicle operator a detailed map showing the vehicle location, a desired destination, and the geographic details of the surrounding area. Under certain situations, the vehicle operator has the opportunity to study the map in exact and thorough detail. An example is a parked vehicle. There are other times, however, when the vehicle operator is too busy operating the vehicle to safely view the displayed information, let alone study the displayed information in exacting detail. This is particularly the case where the vehicle operator is in the midst of a particularly taxing circumstance, for example, driving in heavy traffic, driving at a high speed, or otherwise distracted by an emergency situation or telephone conversation. In such situations, the display presentation distracts the vehicle operator because the operator focuses attention on the details shown on the display.

Therefore, there exists a need to provide valuable and timely travel-related information to a vehicle operator while minimizing potentially dangerous distractions to the vehicle operator.

SUMMARY OF THE INVENTION

The present invention is a system and method for reviewing inputted voice instructions in a vehicle-based telematics control unit. The system includes a microphone, a speech recognition processor, and an output device. The microphone receives voice instructions from a user. Coupled to the microphone is the speech recognition processor that generates a voice signal by performing speech recognition processing of the received voice instructions. The output device outputs the generated voice signal to the user. The system also includes a user interface for allowing the user to approve the outputted voice signal, and a communication component for wirelessly sending the generated voice signal to a server over a wireless network upon approval by the user.

In accordance with further aspects of the invention, a first component generates a digest including the generated voice signal, and a second component sends the digest to a human operator system.

In accordance with other aspects of the invention, a text generator generates text from the generated voice signal, and the output device includes a display that presents the generated text.

In accordance with still further aspects of the invention, a voice synthesizer generates speech based on the generated voice signal, and the output device includes at least one speaker for presenting the generated voice.

As will be readily appreciated from the foregoing summary, the invention provides a feedback system for ensuring accuracy when providing voice instructions.

BRIEF DESCRIPTION OF THE DRAWINGS

The preferred and alternative embodiments of the present invention are described in detail below with reference to the following drawings.

FIG. 1 is a block diagram illustrating the components of the present invention;

FIG. 2 is a flow chart illustrating the present invention performed by the device shown inFIG. 1;

FIG. 3 is a flow chart illustrating the operation of a specific example of the present invention;

FIG. 4 is a block diagram illustrating the components of an alternate embodiment of the present invention; and

FIG. 5 is a flow chart illustrating the present invention performed by the device shown inFIG. 4.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT

The present invention provides a system, method, and computer program product for modulating output over output devices (e.g., display, speakers) based on present vehicle conditions (e.g., speed, rate of change in speed or direction, emergencies). When the system determines that the vehicle requires a more attentive operator, the method of the present invention manipulates the format of information and content presented to the vehicle operator via the output devices.

FIG. 1 shows asystem20, a telematics control unit, within a vehicle that performs the present invention.System20 includes auser interface22 having amicrophone24 for capturing the user's voice; adisplay26;speakers28; and aninterface entry30 for allowing the user to perform various interactive functions.System20 also includes aprocessor32; a global positioning system (GPS)34 for determining precise vehicle locations; and acommunications device36, such as a cellular modem, for transmitting and receiving wireless information.System20 is also coupled to receive information from other vehicle systems (not shown), such as a speedometer, an engine, or a braking system.

FIG. 2 illustrates a preferred process performed bysystem20. Atblock60,system20 and, more specifically,processor32, receives presentation content. The presentation content is preferably received atcommunications device36 from a server transmitted over a network (not shown). Atdecision block62,processor32 determines if any vehicle emergency condition exists based on information received from the other vehicle systems. Ifprocessor32 determines that a vehicle emergency condition exists,processor32 stops all output of received presentation content to any one of the components of user interface22 (block64). Examples of a vehicle emergency condition that may cause the processor to stop output presentation content touser interface22 are signals received from the engine that indicate engine overheating or a signal that indicates the operator has applied brakes to the point where an anti-braking system is activated.

If, atdecision block62,processor32 determines that there is not a vehicle emergency condition,processor32 receives vehicle condition information (block66). The vehicle condition information comes from a number of sources that generate signals, such asGPS34 or a speedometer. Atblock68,processor32 outputs presentation content throughuser interface22 based on the vehicle condition information. This step involves determining the substance and format of the presentation content to display ondisplay26 or broadcast onspeakers28 ofuser interface22. For example, when the vehicle is parked,processor32 presents all or nearly all of the received presentation content. As the vehicle condition changes, for example, the vehicle picks up speed,processor32 changes the presentation content information that is shown ondisplay26. The change in presentation content may also involve shifting presentation of information from visual display to audio broadcast as output throughspeakers28. In one example, the presented content is a full detailed map of the vehicle's location that includes directions to a previously requested destination. Based on the vehicle speed, or the rate of change in vehicle speed or direction, the detail shown on the map will be altered. As the vehicle speed increases, the detail shown on the map is reduced, for example, to include only the vehicle's present location in relation to nearby streets or intersections. Some or all of the presentation content, or map directions, may be translated to audio format and broadcast to the vehicle operator viaspeakers28. In other examples, change in vehicle condition may result in alteration of the font or size of text, icons and graphics presented on the display, as well as increased or decreased audio broadcast.FIG. 3 illustrates an example, based on vehicle speed, of howprocessor32 changes the output that is presented overuser interface22.

Afterblocks64 and68,processor32 returns to block60 to continue receiving more presentation content. In this embodiment, presentation content is processed in real-time from the time of reception from the server over the network to the output of presentation content to a vehicle operator throughuser interface22. In an alternate embodiment, the presentation content can be received all at one time and stored byprocessor32 before any determination is made of how to present the output. In another alternate embodiment, if a person other than the vehicle operator wishes to view the presentation content, presented output is set to whatever level of detail is desired.

FIG. 3 illustrates an example of the process performed atblock68 ofFIG. 2. At block80, vehicle speed information is determined, for example by reference to the vehicle speedometer. If the vehicle's speed is less than or equal to 25 mph,processor32 generates a detailed display to present ondisplay26 of user interface22 (block82). As the speed of the vehicle increases, the amount of detailed visual information generated for display is reduced. Thus, if the vehicle speed is greater than 25 mph but less than or equal to 40 mph,processor32 generates a display with less visual information than was generated for vehicle speeds of less than or equal to 25 mph (block84). When the speed is greater than 40 mph but less than or equal to 70 mph,processor32 reduces not only the amount of detail to be displayed ondisplay26, but also increases the font size of any text included in the displayed presentation content and changes the color to make it easier for an operator to view (block86). When the speed is greater than 70 mph,processor32 stops generating display information for presentation ondisplay26 and switches to a pure audio presentation for output over the speakers28 (block88). The specific speed ranges described are exemplary only. The exact trigger speeds may vary according to various factors, such as road conditions, vehicle specification, vehicle operator skill, etc., as well as user preference. Likewise, the output format of the presentation content may be varied according to user interface hardware or software constraints as well as user preference.

In addition to the example described above with reference to overall vehicle speed, presentation content can be automatically adjusted based upon one or more vehicle conditions related to rate of change in vehicle speed, rate of change in vehicle direction, cellular phone or headphone activation, radar detector activation, noise level decibels above a certain value, radio/CD player in use, TV/DVD console in use, turn signal, etc. The vehicle conditions are determined by vehicle systems, such as the vehicle speedometer, steering, engine, and braking and acceleration systems. Vehicle systems may also include additional components, such as temperature, humidity, wind speed and precipitation gauges, a compass, clock, etc. These additional vehicle system components may be integrated with or separate fromsystem20, so long as they are capable of being monitored bysystem20. The method of the present invention automatically adjusts the output of presentation content based upon a monitor of these vehicle conditions, or a combination of these vehicle conditions. For example,system20 monitors vehicle braking and acceleration systems with reference to an internal clock to determine the rate of change of vehicle speed. If vehicle speed is increasing or decreasing rapidly,system20 automatically reduces the amount of detail provided in visual presentation content, and may transfer some or all of the content to audio presentation. In another example,system20 monitors movement of the steering wheel and vehicle direction with reference to a compass and a clock to determine rate of change of vehicle direction. If vehicle direction is changing rapidly,system20 would again automatically reduce the amount of detail provided in visual presentation content, as well as transfer some or all of the content to audio presentation.

FIG. 4 illustrates avehicle system120, a telematics control unit, that performs an alternate embodiment of the present invention.Vehicle system120 includes auser interface122 and aprocessor124.User interface122 includes a microphone that receives voice instructions from a user and sends them toprocessor124.Processor124 performs voice processing of the received voice signals. The processor outputs the processed voice signals over speakers or a display that are part ofuser interface122. Also,processor124 sends the processed voice signals to anoperator142 at anoperator system140 over awireless network130.

FIG. 5 illustrates a process performed bysystem120 shown inFIG. 4. First, atblock210, the user inputs voice instructions to system120 (processor124) viauser interface122. Next, atblock212,processor124 performs voice recognition processing on the received voice instructions to determine the content of the inputted instructions. The result of the voice recognition processing is presented to the user viauser interface122 in the form of voice over speakers or text on a display (block214). Ifprocessor124 has interpreted the inputted voice instructions properly, as shown indecision block216, the user instructssystem120 to send the processed instructions to a predefined destination (block218). The predefined destination is preferably a system server. Otherwise, the user has the opportunity to contact a human operator to make sure the instructions are properly entered (decision block220). If the user decides to contact the human operator, a digest of the interaction between the user andprocessor124 is sent to human operator system140 (block222). Then, atblock224, the user is connected to the human operator who is tending a phone and/or computer terminal. At this point the user and human operator resolve the content of the user-initiated instructions. If at thedecision block220 the user does not approve of the presented voice instructions or desire to be connected to a human operator, the user can return to providing new voice instructions (block210).

In an alternate embodiment,processor124 processes a received voice instruction based on previously recorded prior processing of the same voice instruction. For example, at five previous episodes, the user provided a certain voice instruction about a restaurant.Processor124 made a first determination as to what the user requested for each of the five episodes. In the first four of the five episodes, the user desired directions to the restaurant. In the fifth episode, the user desired stock information about the publicly traded company by the same name that owns the restaurant. The approved results (four directions; one stock information) of the processed voice instruction are recorded atprocessor124 with the voice instruction for each episode. The next time the user provides that same voice instruction,processor124 uses the previously recorded approved results when processing the voice instruction. Various methods of using the previously recorded approved results can be performed. In a first method, the most frequent recorded result becomes the result of the newly provided specific voice instruction. So, using the example above, directions are provided to the user, because the recorded results show requests for directions to the restaurant (as opposed to requests for stock information) occurring more frequently. In a second method, the most recent recorded result becomes the result of the newly provided specific voice instruction. So, using the example above, stock information is provided to the user, because the last recorded result was stock information.

With respect to the first four episodes described above,processor124 processed the voice instruction as either a request for directions or as a request for something other than directions. If the voice instruction was processed as a request for directions, the user approves of the processing, and the resulting request for directions to the restaurant is recorded with the voice instruction for the episode. If the voice instruction was processed as a request for something other than directions, the user makes a request thatprocessor124 provide directions, thereby indicating that the processing of the voice instructions was incorrect. The user can indicate that the processing was incorrect (and in this example that directions were desired) in a number of different ways. One way to make a change request is to contact a human operator (decision block220 ofFIG. 5). The human operator makes the change for that episode, and the change is recorded. Another way is to make a subsequent voiceinstruction requesting processor124 to reinterpret the original voice instruction. Once the voice instruction has changed to a request for directions and the user approves of the change, the result of directions to the restaurant is recorded with the voice instruction for that episode.

While the preferred embodiment of the invention has been illustrated and described, as noted above, many changes can be made without departing from the spirit and scope of the invention. For example, as noted above, the trigger event or threshold used to determine the output format of presentation content, as well as the specific output format, might vary according to different factors as well as user preference. Accordingly, the scope of the invention is not limited by the disclosure of the preferred embodiment. Instead, the invention should be determined entirely by reference to the claims that follow.

Claims (5)

1. A system for reviewing inputted voice instructions in a vehicle-based telematics control unit located in a vehicle, the system comprising:

a microphone for receiving voice instructions from a user;

a speech recognition processor coupled to the microphone for generating a voice signal by performing speech recognition processing of the received voice instructions;

an output device for outputting the generated voice signal to the user; and

a first processor configured to determine if an emergency condition of the vehicle exists, and, if an emergency condition of the vehicle does exist, to prevent the output device from outputting the generated voice signal to the user.

2. The system ofclaim 1, further comprising: a user interface for allowing the user to approve of the outputted voice signal; and a communication component for wirelessly sending the generated voice signal to a server over a wireless network upon approval by the user.

3. The system ofclaim 1, further comprising: a first component for generating a digest including the generated voice signal; and a second component for sending the digest to a human operator system.

4. The system ofclaim 1, further comprising a text generator for generating text from the generated voice signal, wherein the output device includes a display for presenting the generated text.

5. The system ofclaim 1, further comprising a voice synthesizer for generating voice based on the generated voice signal, wherein the output device includes at least one speaker for presenting the generated voice.

Images